Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Near-Field Multiuser Beam-Training for Extremely Large-Scale MIMO Systems

Wang Liu, Cunhua Pan, Hong Ren, Jiangzhou Wang, Robert Schober, Lajos Hanzo

TL;DR

A three-phase graph neural network (GNN)-based beam training scheme for multiuser XL-MIMO systems that significantly improves beam training accuracy and reduces pilot overhead compared to traditional neural network-based benchmarks is conceived.

Abstract

Extremely large-scale multiple-input multiple-output (XL-MIMO) systems are capable of improving spectral efficiency by employing far more antennas than conventional massive MIMO at the base station (BS). However, beam training in multiuser XL-MIMO systems is challenging. To tackle these issues, we conceive a three-phase graph neural network (GNN)-based beam training scheme for multiuser XL-MIMO systems. In the first phase, only far-field wide beams have to be tested for each user and the GNN is utilized to map the beamforming gain information of the far-field wide beams to the optimal near-field beam for each user. In addition, the proposed GNN-based scheme can exploit the position-correlation between adjacent users for further improvement of the accuracy of beam training. In the second phase, a beam allocation scheme based on the probability vectors produced at the outputs of GNNs is proposed to address the above beam-direction conflicts between users. In the third phase, the hybrid TBF is designed for further reducing the inter-user interference. Our simulation results show that the proposed scheme improves the beam training performance of the benchmarks. Moreover, the performance of the proposed beam training scheme approaches that of an exhaustive search, despite requiring only about 7% of the pilot overhead.

Near-Field Multiuser Beam-Training for Extremely Large-Scale MIMO Systems

TL;DR

A three-phase graph neural network (GNN)-based beam training scheme for multiuser XL-MIMO systems that significantly improves beam training accuracy and reduces pilot overhead compared to traditional neural network-based benchmarks is conceived.

Abstract

Extremely large-scale multiple-input multiple-output (XL-MIMO) systems are capable of improving spectral efficiency by employing far more antennas than conventional massive MIMO at the base station (BS). However, beam training in multiuser XL-MIMO systems is challenging. To tackle these issues, we conceive a three-phase graph neural network (GNN)-based beam training scheme for multiuser XL-MIMO systems. In the first phase, only far-field wide beams have to be tested for each user and the GNN is utilized to map the beamforming gain information of the far-field wide beams to the optimal near-field beam for each user. In addition, the proposed GNN-based scheme can exploit the position-correlation between adjacent users for further improvement of the accuracy of beam training. In the second phase, a beam allocation scheme based on the probability vectors produced at the outputs of GNNs is proposed to address the above beam-direction conflicts between users. In the third phase, the hybrid TBF is designed for further reducing the inter-user interference. Our simulation results show that the proposed scheme improves the beam training performance of the benchmarks. Moreover, the performance of the proposed beam training scheme approaches that of an exhaustive search, despite requiring only about 7% of the pilot overhead.
Paper Structure (17 sections, 32 equations, 12 figures, 1 table, 2 algorithms)

This paper contains 17 sections, 32 equations, 12 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. State-of-the-art
  3. Main Contributions
  4. System Model
  5. Signal Model
  6. Near-Field Channel Model
  7. Problem Formulation
  8. Three-phase GNN-based Beam Training
  9. UL Pilot Transmission
  10. Architecture of GNN-based Estimation Network
  11. Three-Phase GNN-based Beam training
  12. Computational Complexity
  13. Simulation Results
  14. System Setup
  15. Metrics and Benchmarks
  16. ...and 2 more sections

Figures (12)

  • Figure 1: Hybrid precoding architecture for multiuser XL-MIMO system.
  • Figure 2: Near-field codebook with angle sampling and distance sampling.
  • Figure 3: Overall architecture of GNN-based estimation network.
  • Figure 4: Neighbouring users' beamforming gain information is mutually correlated, as they share the wireless propagation environment.
  • Figure 5: Proposed three-phase GNN-based beam training.
  • ...and 7 more figures